AI Paper Atlas

Research map / Reinforcement learning / RL from feedback

Joint Alignment and Distillation for Video Generation via Sample-Guided Distribution Matching

Jiuzhou Lin, Fei Zuo, Huan Ouyang, Junlong Wu, Dewen Fan, Boheng Zhang, Huaiqing Wang, Jia Sun, Fan Yang, Houde Liu, Kehai Chen, Min Zhang and 2 more

ECCV 2026 · Reinforcement learning › RL from feedback · approach: RL fine-tuning of generative models · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
single-stage DM-Align (Pair) instead of raw modelWan2.1-T2V-1.3B · VBench (ConsistID, Pair)Average score: 78.20 -> 82.78Improved
single-stage DM-Align (Group) instead of raw modelWan2.1-T2V-1.3B · VBench (VidProM, Group)Average score: 77.85 -> 84.40Improved
apply DMD2 distillation after Flow-DPO (two-stage)Flow-DPO · VBench (ConsistID, Pair)Dynamic Degree: 67.13 -> 53.43Hurt
apply DMD2 distillation after DanceGRPO (two-stage)DanceGRPO · VBench (VidProM, Group)Dynamic Degree: 75.78 -> 60.85Hurt
joint DM-Align instead of two-stage Flow-DPO + DMD2DM-Align (Pair) · VBench (ConsistID, Pair)Average score: 79.89 -> 82.78Improved
joint DM-Align instead of two-stage DanceGRPO + DMD2DM-Align (Group) · VBench (VidProM, Group)Average score: 80.54 -> 84.40Improved
DM-Align vs DanceGRPO training step costDM-Align · Training efficiencytime per step (s): 423 -> 15Improved
apply DM-Align to Wan2.2-A14B MoE (high-noise expert)Wan2.2-T2V-A14B · VBench (Wan2.2-A14B MoE)VBench score: 78.35 -> 83.45Improved
add alignment loss with 1:1 weight to DMD (ablation)DM-Align (Wan-1.3B) · Loss weight sensitivity (HPSv2)HPSv2: 20.50 -> 28.89Improved
raise alignment weight to 1:3 (low DMD weight) (ablation)DM-Align (Wan-1.3B) · Loss weight sensitivity (HPSv2)HPSv2: 28.89 -> 12.37Hurt
linear scheduling of weights from 1:0 to 1:3 instead of 1:1 (ablation)DM-Align (Wan-1.3B) · Loss weight sensitivity (TA)TA: 1.65 -> 1.45Hurt
add DM-Align on CogVideoX-2B vs DMD only (ablation)CogVideoX-2B · Loss weight sensitivity (HPSv2)HPSv2: 18.71 -> 25.01Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy